DR stands for dimensionality reduction. In machine learning, dimensionality reduction is a feature engineering technique, in which a large number of features in a dataset is reduced to a smaller number of features. It is important to ensure that the remaining features are meaningful and representative for the dataset and that only irrelevant and missing features are removed. Dimensionality reduction achieves the reduction of "dimensions" of a dataset, i.e. the reduction of the number of features which are present in the dataset.
A large number of features in a dataset can lead to the curse of dimensionality, according to which, in order to increase the precision of a model, the number of features in a dataset must theoretically increase exponentially, but that in itself dramatically increases model training time and the model suffers from overfitting to data and does not generalize well.
